Abstract
ESR Endangered Species Research Contact the journal Facebook Twitter RSS Mailing List Subscribe to our mailing list via Mailchimp HomeLatest VolumeAbout the JournalEditorsSpecials ESR 36:89-98 (2018) - DOI: https://doi.org/10.3354/esr00894 ESR Special: Marine pollution and endangered species A machine-learning approach to assign species to ‘unidentified’ entangled whales James V. Carretta* Southwest Fisheries Science Center, National Oceanic and Atmospheric Administration, 8901 La Jolla Shores Drive, La Jolla, CA 92037, USA *Corresponding author: jim.carretta@noaa.gov ABSTRACT: Whale entanglements in US west coast fishing gear are largely represented by opportunistic sightings, and some reports lack species identifications due to rough seas, distance from whales, or a lack of cetacean identification expertise. Unidentified entanglements are often ignored in species risk assessments and thus, entanglement risk is underestimated. To address this negative bias, a species identification model was built from random forest (RF) classification trees using 199 identified entanglements (‘model data’). Humpback Megaptera novaeangliae and gray whales Eschrichtius robustus represented 92% of identified entanglements; the remaining 8% were minke whales Balaenoptera acutorostrata, fin whales B. physalus, blue whales B. musculus, and sperm whales Physeter macrocephalus. Predictor variables included year, gear type, location, season, sea surface temperature, water depth, and a multivariate El Niño index. Cross-validated species classifications were correct in 78% (155/199) of cases, significantly higher (p < 0.001, permutation test) than the 49% correct classification rate expected by chance. The RF model correctly classified 91% of humpback whale cases, 64% of gray whale cases, and 100% of sperm whale cases, but misclassified all minke, blue, and fin whale cases. The cross-validated RF classification-tree species model was used to classify 35 entanglements without species identifications (‘novel data’) and each case was assigned a probability of belonging to each of 6 model data species. This approach eliminates the negative bias associated with ignoring unidentified entanglements in species risk assessments. Applications to other wildlife studies where some detections are unidentified include fisheries bycatch, line-transect surveys, and large-whale vessel strikes. KEY WORDS: Fishery entanglement · Humpback whale · Gray whale · Species assignment · Random forest Full text in pdf format PreviousNextCite this article as: Carretta JV (2018) A machine-learning approach to assign species to ‘unidentified’ entangled whales. Endang Species Res 36:89-98. https://doi.org/10.3354/esr00894 Export citation Mail this link - Contents Mailing Lists - RSS Facebook - Tweet - linkedIn Cited by Published in ESR Vol. 36. Online publication date: June 13, 2018 Print ISSN: 1863-5407; Online ISSN: 1613-4796 Copyright © 2018 Inter-Research.
Highlights
Entanglement of large whales in fishing gear and marine debris is a source of anthropogenic mortality and serious injury worldwide (Read et al 2006, Bradford et al 2009, Cassoff et al 2011, Meÿer et al 2011, Groom & Coughran 2012, Knowlton et al 2012, Moore 2014, van der Hoop et al 2017)
High rates of correct species classification from the random forest (RF) model are largely due to differences in seasonal occurrence of gray and humpback whales, proportions of entanglements involving net versus pot/trap gear, and the locations of the observed entanglements (Table 3)
The correct classification of both sperm whale model data cases was initially surprising because they represent only 1% of model data cases and such minor response classes are usually misclassified at a nearly 100% rate. Both sperm whale entanglements occurred in the same gillnet fishing set and cannot be considered independent events because they involved whales from the same social group entangled at the same time and location
Summary
Entanglement of large whales in fishing gear and marine debris is a source of anthropogenic mortality and serious injury worldwide (Read et al 2006, Bradford et al 2009, Cassoff et al 2011, Meÿer et al 2011, Groom & Coughran 2012, Knowlton et al 2012, Moore 2014, van der Hoop et al 2017). Documented entanglements represent a minimum accounting of impacts, because not all at-sea entanglements are detected; either the whale is never seen or observers fail to recognize that a whale is entangled. Negative reporting biases are not limited to at-sea sightings. Endang Species Res 36: 89–98, 2018 whales, or a lack of whale identification expertise (Carretta et al 2016b). Quantitative methods to prorate unidentified cases to species are lacking in US marine mammal stock assessments (Muto et al 2016, Waring et al 2016, Carretta et al 2017); the perceived entanglement risk to some species is negatively biased via omission of these cases. To better account for entanglement risk, I developed a species classification model using random forest (RF) classification trees (Breiman 2001a,b, Liaw & Wiener 2002), which are used to classify unidentified sightings of entangled whales to species
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have